|
Confidence intervals estimation for survival function in
Weibull proportional hazards regression based on censored
survival time data
Kamil Alakuş
Department of Statistics, Faculty of science and Arts,
Ondokuz Mayıs University, 55139 Kurupelit- Samsun, Turkey.
E-mail:
kamilalakus@gmail.com.
Tel: +90 362 312 19 19/ 5231.
Accepted 4 June, 2010 |
|
Weibull distribution plays a central role in the analysis of
survival or life time data. Link (1984, 1986) presented a
confidence interval estimate of survival function using
Cox’s proportional hazard model with covariates. Her idea
more recently extended by Alakuş et al. (2007) to the
exponential distribution and Alakuş et al. (2007) to
exponential proportional hazard model, respectively. Alakuş
(2010) studied confidence intervals for survival function
from Weibull distribution. The same idea may be extended to
the Weibull proportional hazard model provided that the
survival times have a Weibull distributed random variable.
In this study, we formed confidence interval for Weibull
survival function for any values of the time and the
covariates. Real data examples are also considered for
illustrating the discussed confidence interval.
Key words: Confidence interval, hazard
function, point estimation, survival analysis, survival
function, Weibull distribution, Weibull proportional hazard
model. |
